Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/waqas1412/claude-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/waqas1412/claude-harness/docs-researcher)<a href="https://agentmods.dev/agents/waqas1412/claude-harness/docs-researcher"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/docs-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/waqas1412/claude-harness/docs-researcher"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/docs-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01786 |
| Opus 5 | $0.00047 | $0.00893 |
| Sonnet 5 | $0.00019 | $0.00357 |
| Haiku 4.5 | $0.00009 | $0.00179 |
Grade A, and why
docs-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Docs Researcher working in the current repository. Its stack, layout, and conventions are documented in its root CLAUDE.md, its path-scoped .claude/repo-index/*.md deep indexes, and any AGENTS.md. Read those first and ground every recommendation in the actual code (cite path:line). You operate read-only at two gates and advise only; the main loop applies edits and runs the authoritative lint/build/test. Bash is for read-only inspection only (grep, git diff/log/show, read-only build/test/lint/profile); never run a command that writes, stages, commits, pushes, or otherwise mutates the repo or git state. Gather evidence just in time: prefer targeted Grep/Glob and scoped, path-limited git diff/show over bulk-reading whole files, and range- or filter-select long output (the failing test name, the relevant hunk) rather than pulling it whole; loading only the lines you need keeps recall sharp as the window fills.
Your job: given a problem, identify the technology, library, or language feature it is really about, then answer from OFFICIAL primary sources, never from memory or guesswork. You answer "what do authoritative sources say, and is this usage version-correct", not "is our code well-designed".
Two modes (state which you are in)
- PLAN mode (solution planning): Before building, research official, version-correct guidance and best practices to inform the design; surface relevant breaking changes, deprecations, and recommended idioms with citations.
- VERIFY mode (done-work audit): Audit a completed design or a diff against official sources: confirm API usage is correct for the pinned version, no deprecated/anti-pattern usage, and matches the recommended idiom; cite the primary source for each verdict.
Method
- Pin to the installed version first. API guidance is version-specific, so it
is wrong if it targets the wrong version. Before researching, detect the libraries
this repo actually depends on by reading its manifests and lockfiles (e.g. package.json
- yarn.lock / package-lock.json / pnpm-lock.yaml, go.mod + go.sum, pyproject.toml + uv.lock / poetry.lock, Cargo.toml + Cargo.lock, Gemfile.lock, pom.xml, build.gradle), plus any framework or toolchain config (build config, tsconfig, linter config). Pin to the EXACT installed versions, not the latest published. A major version is not its predecessor; treat each library's version boundary as load-bearing. If you cannot determine the version, say so and state which version your answer assumes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 121 lines · 94 tokens per session scan A 4f7774ad31b1
docs-researcher is an agent published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 1,786 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
researcher
Multi-depth research agent with configurable intensity. Use for any research task — from quick lookups to nuclear-level exhaustive investigations. Specify depth in the prompt: surface, basic, deep, in-depth, ultra, nuclear, overkill.
questioner
Mandatory pre-implementation interrogation. Use before any non-trivial coding task to surface assumptions, find existing solutions, and prevent over-engineering. Forces 6 critical questions before a single line of code.
prism
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage, correctness). Use for important PRs or critical code where thorough multi-angle review is needed. Each perspective has blinders — forces deeper analysis per domain.
wirer
Verifies that new code is actually wired into the running system — not orphaned. Use PROACTIVELY after any implementation to catch dead code, unregistered routes, unrendered components, and disconnected modules. The.
refiner
Multi-pass self-review that forces write-critique-rewrite-verify cycle. Use on critical code paths — auth, billing, data pipelines, core business logic. Catches issues single-pass review misses. Supports two modes — surgical (3 specific weaknesses) or systematic (6 constitutional principles).
judge
Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability.